agent-setup
Warn
Audited by Snyk on Feb 15, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). The skill explicitly directs fetching a recipe from the public site https://fullstackrecipes.com/api/recipes/agent-setup (via curl), causing the agent to ingest and interpret content from an external, untrusted web source and therefore enabling indirect prompt injection.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.90). This skill instructs fetching a runtime recipe from https://fullstackrecipes.com/api/recipes/agent-setup, which would supply agent configuration/instructions that directly control the agent's prompts and is presented as a required fallback dependency.
Audit Metadata